© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93990
    Prev
    Next
    INDEX
    Explanations

    work and contribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     хуже
    -0.90
    んだん
    -0.90
     affordability
    -0.84
    ↄ
    -0.84
     выбор
    -0.83
    ニューアル
    -0.83
    ゥ
    -0.82
    usercontent
    -0.81
    ილ
    -0.79
    ogada
    -0.79
    POSITIVE LOGITS
     contribute
    1.44
     working
    1.20
     contribution
    1.20
     work
    1.20
     contributing
    1.16
     performance
    1.16
     contributed
    1.14
     contributes
    1.12
     their
    1.07
     contributions
    1.07
    Activations Density 0.035%

    No Known Activations